> ## Documentation Index
> Fetch the complete documentation index at: https://docs.ag2.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# autogen.agentchat.contrib.capabilities.text_compressors.LLMLingua

<h2 id="autogen.agentchat.contrib.capabilities.text_compressors.LLMLingua" class="doc doc-heading">
  <code class="doc-symbol doc-symbol-heading doc-symbol-class" />

  <span class="doc doc-object-name doc-class-name">LLMLingua</span>
</h2>

```python theme={null}
LLMLingua(prompt_compressor_kwargs: dict = {'model_name': 'microsoft/llmlingua-2-bert-base-multilingual-cased-meetingbank', 'use_llmlingua2': True, 'device_map': 'cpu'}, structured_compression: bool = False)
```

Compresses text messages using LLMLingua for improved efficiency in processing and response generation.<br />NOTE: The effectiveness of compression and the resultant token savings can vary based on the content of the messages
and the specific configurations used for the PromptCompressor.<br />

<b>Parameters:</b>

| Name                       | Description                                            |
| -------------------------- | ------------------------------------------------------ |
| `prompt_compressor_kwargs` | **Type:** dict<br /><br />**Default:** \{'model\_name' |
| `structured_compression`   | **Type:** bool<br /><br />**Default:** False           |

### Instance Methods

<code class="doc-symbol doc-symbol-heading doc-symbol-method" />

#### compress\_text

```python theme={null}
compress_text(
    self,
    text: str,
    **compression_params
) -> dict[str, Any]
```

<b>Parameters:</b>

| Name                   | Description   |
| ---------------------- | ------------- |
| `text`                 | **Type:** str |
| `**compression_params` |               |

<br />